[root@node1 ~]# ceph -s
cluster:
id: 52feab00-22e8-4f98-9840-6d9778d88d09
health: HEALTH_ERR
64/4832148 objects unfound (0.001%)
Possible data damage: 21 pgs recovery_unfound
Degraded data redundancy: 94544/9664755 objects degraded (0.978%), 21 pgs degraded, 21 pgs undersized
services:
mon: 3 daemons, quorum b,g,h (age 3w)
mgr: a(active, since 3w)
osd: 52 osds: 51 up (since 73m), 50 in (since 4w); 21 remapped pgs
rgw: 4 daemons active (4 hosts, 1 zones)
data:
pools: 25 pools, 1521 pgs
objects: 4.83M objects, 19 TiB
usage: 40 TiB used, 57 TiB / 97 TiB avail
pgs: 94544/9664755 objects degraded (0.978%)
64/4832148 objects unfound (0.001%)
1498 active+clean
21 active+recovery_unfound+undersized+degraded+remapped
2 active+clean+scrubbing+deep+repair
io:
client: 660 KiB/s rd, 5.0 MiB/s wr, 104 op/s rd, 481 op/s wr
[root@node1 ~]# ceph pg dump_stuck
ok
PG_STAT STATE UP UP_PRIMARY ACTING ACTING_PRIMARY
52.1fd active+recovery_unfound+undersized+degraded+remapped [36,21] 36 [21] 21
52.1cf active+recovery_unfound+undersized+degraded+remapped [36,27] 36 [27] 27
12.71 active+recovery_unfound+undersized+degraded+remapped [34,13] 34 [13] 13
12.cd active+recovery_unfound+undersized+degraded+remapped [11,3] 11 [3] 3
12.b6 active+recovery_unfound+undersized+degraded+remapped [31,39] 31 [39] 39
12.4f active+recovery_unfound+undersized+degraded+remapped [33,46] 33 [46] 46
12.fc active+recovery_unfound+undersized+degraded+remapped [29,16] 29 [16] 16
12.e4 active+recovery_unfound+undersized+degraded+remapped [11,47] 11 [47] 47
12.ba active+recovery_unfound+undersized+degraded+remapped [31,7] 31 [7] 7
12.c0 active+recovery_unfound+undersized+degraded+remapped [11,22] 11 [22] 22
12.ab active+recovery_unfound+undersized+degraded+remapped [33,15] 33 [15] 15
12.96 active+recovery_unfound+undersized+degraded+remapped [23,18] 23 [18] 18
87.43 active+recovery_unfound+undersized+degraded+remapped [35,50] 35 [50] 50
52.11 active+recovery_unfound+undersized+degraded+remapped [41,52] 41 [52] 52
12.6e active+recovery_unfound+undersized+degraded+remapped [31,6] 31 [6] 6
12.dd active+recovery_unfound+undersized+degraded+remapped [11,37] 11 [37] 37
52.2c active+recovery_unfound+undersized+degraded+remapped [36,27] 36 [27] 27
52.d9 active+recovery_unfound+undersized+degraded+remapped [41,27] 41 [27] 27
12.55 active+recovery_unfound+undersized+degraded+remapped [33,45] 33 [45] 45
12.5f active+recovery_unfound+undersized+degraded+remapped [33,45] 33 [45] 45
52.67 active+recovery_unfound+undersized+degraded+remapped [36,21] 36 [21] 21
# UP_PRIMARY 对应的是osd
存在一些pg有问题，ceph是一个自修复（某种程度上）的系统，可以看到数据应该正在从36 迁移到 21，所以UP_PRIMARY 的osd应该是有点问题的
[root@node1 ~]# ceph pg 52.1fd query | grep osd
"osd": "36",
参考，可能需要重建有问题的pg: https://www.antute.com.cn/index.php?id=258
